Caroline Marc, Bertrand Marcon, Louis Denaud, Stéphane Girardon
{"title":"基于u - net深度学习的均匀木单板车床检测自动检测","authors":"Caroline Marc, Bertrand Marcon, Louis Denaud, Stéphane Girardon","doi":"10.1007/s00107-025-02208-0","DOIUrl":null,"url":null,"abstract":"<div><p>Automated detection of lathe checks in wood veneers presents significant challenges due to their variability and the natural properties of wood. This study explores the use of two convolutional neural networks (U-Net architecture) to enhance the precision and efficiency of lathe checks detection in poplar veneers. The approach involves sequential application of two U-Nets: the first for detecting lathe checks through semantic segmentation, and the second for refining these predictions by connecting fragmented lathe checks. Post-processing techniques are applied to denoise the mappings and extract precise lathe check characteristics. The first U-Net demonstrated strong performance in predicting lathe check presence, with precision and recall scores of 0.822 and 0.835, respectively. The second U-Net refined predictions by linking disjointed segments, improving the overall lathe checks mapping process. Comparative analysis with manual methods revealed comparable or superior performance of the automated approach, especially for shallow lathe checks. The results highlight the potential of the proposed method for efficient and reliable lathe check detection in wood veneers.</p></div>","PeriodicalId":550,"journal":{"name":"European Journal of Wood and Wood Products","volume":"83 2","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s00107-025-02208-0.pdf","citationCount":"0","resultStr":"{\"title\":\"U-NET-based deep learning for automated detection of lathe checks in homogeneous wood veneers\",\"authors\":\"Caroline Marc, Bertrand Marcon, Louis Denaud, Stéphane Girardon\",\"doi\":\"10.1007/s00107-025-02208-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Automated detection of lathe checks in wood veneers presents significant challenges due to their variability and the natural properties of wood. This study explores the use of two convolutional neural networks (U-Net architecture) to enhance the precision and efficiency of lathe checks detection in poplar veneers. The approach involves sequential application of two U-Nets: the first for detecting lathe checks through semantic segmentation, and the second for refining these predictions by connecting fragmented lathe checks. Post-processing techniques are applied to denoise the mappings and extract precise lathe check characteristics. The first U-Net demonstrated strong performance in predicting lathe check presence, with precision and recall scores of 0.822 and 0.835, respectively. The second U-Net refined predictions by linking disjointed segments, improving the overall lathe checks mapping process. Comparative analysis with manual methods revealed comparable or superior performance of the automated approach, especially for shallow lathe checks. The results highlight the potential of the proposed method for efficient and reliable lathe check detection in wood veneers.</p></div>\",\"PeriodicalId\":550,\"journal\":{\"name\":\"European Journal of Wood and Wood Products\",\"volume\":\"83 2\",\"pages\":\"\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2025-02-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://link.springer.com/content/pdf/10.1007/s00107-025-02208-0.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European Journal of Wood and Wood Products\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s00107-025-02208-0\",\"RegionNum\":3,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"FORESTRY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Wood and Wood Products","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1007/s00107-025-02208-0","RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FORESTRY","Score":null,"Total":0}
U-NET-based deep learning for automated detection of lathe checks in homogeneous wood veneers
Automated detection of lathe checks in wood veneers presents significant challenges due to their variability and the natural properties of wood. This study explores the use of two convolutional neural networks (U-Net architecture) to enhance the precision and efficiency of lathe checks detection in poplar veneers. The approach involves sequential application of two U-Nets: the first for detecting lathe checks through semantic segmentation, and the second for refining these predictions by connecting fragmented lathe checks. Post-processing techniques are applied to denoise the mappings and extract precise lathe check characteristics. The first U-Net demonstrated strong performance in predicting lathe check presence, with precision and recall scores of 0.822 and 0.835, respectively. The second U-Net refined predictions by linking disjointed segments, improving the overall lathe checks mapping process. Comparative analysis with manual methods revealed comparable or superior performance of the automated approach, especially for shallow lathe checks. The results highlight the potential of the proposed method for efficient and reliable lathe check detection in wood veneers.
期刊介绍:
European Journal of Wood and Wood Products reports on original research and new developments in the field of wood and wood products and their biological, chemical, physical as well as mechanical and technological properties, processes and uses. Subjects range from roundwood to wood based products, composite materials and structural applications, with related jointing techniques. Moreover, it deals with wood as a chemical raw material, source of energy as well as with inter-disciplinary aspects of environmental assessment and international markets.
European Journal of Wood and Wood Products aims at promoting international scientific communication and transfer of new technologies from research into practice.